2 September 1993 LCD-based electro-optic implementation of a multilayer perceptron neural network to classify fish species using sonograms as the neural inputs
Author Affiliations +
Abstract
A LCD implementation of a truly analog multilayer perceptron that operates without external control is discussed. The inherent sigmoidal transmissivity transfer function of the LCD is utilized as the neural activation function. The use of photoconductors to directly control the transmissivity of the LCD cells are described, and an accommodation to intensity based negative weights are also noted. A computer simulation program using a curve fitted LCD transfer function (activation function) yielded excellent results in classifying sounds from several endangered and non-endangered species of fish from sonograms of underwater hydrophone recordings. The progress of the hardware implementation is reported.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shinobu Doi, Shinobu Doi, Barry G. Grossman, Barry G. Grossman, } "LCD-based electro-optic implementation of a multilayer perceptron neural network to classify fish species using sonograms as the neural inputs", Proc. SPIE 1965, Applications of Artificial Neural Networks IV, (2 September 1993); doi: 10.1117/12.152568; https://doi.org/10.1117/12.152568
PROCEEDINGS
13 PAGES


SHARE
Back to Top